0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Density Estimation Helps Adversarial Robustness
Authors :
Afsaneh Hasanebrahimi
1
Bahareh Kaviani Baghbaderani
2
Reshad Hosseini
3
Ahmad Kalhor
4
1- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
2- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
3- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
4- College of Engineering, Department of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
Keywords :
Variational Autoencoder،Adversarial Robustness
Abstract :
Adversarial attacks pose a threat to deep learning models, as they involve subtle disturbances that are imperceptible to human vision. In this paper, a classification network is introduced that also includes a density estimation head modeled using the decoder of a variational autoencoder. Incorporating the loss of the variational autoencoder during the training of the classifier aids in achieving a robust latent variable. The experimental findings show that the suggested model successfully defends against various gradient-based adversarial attacks, including FGSM, R-FGSM, MI-FGSM, and PGD, in both scenarios involving white-box and black-box contexts.
Papers List
List of archived papers
Vision-Based Obstacle Avoidance in Drone Navigation using Deep Reinforcement Learning
Pooyan Rahmanzadeh Gervi - Ahad Harati - Sayed Kamaledin Ghiasi-Shirazi
Energy Efficient Power Allocation in MIMO-NOMA Systems with ZF Receiver Beamforming in Multiple Clusters
Mahdi Nangir - Abdolrasoul Sakhaei Gharagezlou - Nima Imani
Enhancing Persian Word Sense Disambiguation with Large Language Models: Techniques and Applications
Fatemeh Zahra Arshia - Saeedeh Sadat Sadidpour
The Effect of Network Environment on Traffic Classification
Abolghasem Rezaei Khesal - Mehdi Teimouri
Enhanced Skin Cancer Classification Using Deep Learning and Gradient Boosting Techniques
Amir Mohammad Sharafaddini - Najme Mansouri
Attention-Boosted Ensemble of Pre-trained Convolutional Neural Networks for Accurate Diabetic Retinopathy Detection
Benyamin Mirab Golkhatmi - Mohammad Hossein Moattar
DPRNN-FORMER: AN EFFICIENT WAY TO DEAL WITH BLIND SOURCE SEPARATION
Ramin Ghorbani - Sajad Haghzad Klidbary
Improving performance of multi-label classification using ensemble of feature selection and outlier detection
Mohammad Ali Zarif - Javad Hamidzadeh
Improving Soft Error Reliability of FPGA-based Deep Neural Networks with Reduced Approximate TMR
Anahita Hosseinkhani - Behnam Ghavami
Information Theoretic Learning-based Deep Embedded Clustering (ITL-DEC)
Hoda Shad - Mona Zamiri - Tahereh Bahreini - Reza Monsefi - Ghoshe Abed Hodtani
more
Samin Hamayesh - Version 41.7.6